Related papers: SQUASH: Serverless and Distributed Quantization-ba…
Retrievers, which form one of the most important recommendation stages, are responsible for efficiently selecting possible positive samples to the later stages under strict latency limitations. Because of this, large-scale systems always…
Serverless computing has emerged as a compelling new paradigm of cloud computing models in recent years. It promises the user services at large scale and low cost while eliminating the need for infrastructure management. On cloud provider…
Modern SoCs integrate multiple CPU cores and Hardware Accelerators (HWAs) that share the same main memory system, causing interference among memory requests from different agents. The result of this interference, if not controlled well, is…
This paper explores resource allocation in serverless cloud computing platforms and proposes an optimization approach for autoscaling systems. Serverless computing relieves users from resource management tasks, enabling focus on application…
Large-scale approximate nearest neighbor search (ANN) has been gaining attention along with the latest machine learning researches employing ANNs. If the data is too large to fit in memory, it is necessary to search for the most similar…
Data deduplication has gained wide acclaim as a mechanism to improve storage efficiency and conserve network bandwidth. Its most critical phase, data chunking, is responsible for the overall space savings achieved via the deduplication…
Quantization has become a mainstream compression technique for reducing model size, computational requirements, and energy consumption for modern deep neural networks (DNNs). With improved numerical support in recent hardware, including…
Vector similarity search plays a pivotal role in modern information retrieval systems, especially when powered by transformer-based embeddings. However, the scalability and efficiency of such systems are often hindered by the high…
Zero-shot Neural Architecture Search (NAS) typically optimises the architecture search process by exploiting the network or gradient properties at initialisation through zero-cost proxies. The existing proxies often rely on labelled data,…
Among many solutions to the high-dimensional approximate nearest neighbor (ANN) search problem, locality sensitive hashing (LSH) is known for its sub-linear query time and robust theoretical guarantee on query accuracy. Traditional LSH…
The use of large-scale machine learning methods is becoming ubiquitous in many applications ranging from business intelligence to self-driving cars. These methods require a complex computation pipeline consisting of various types of…
Traditional approaches to vector similarity search over encrypted data rely on fully homomorphic encryption (FHE) to enable computation without decryption. However, the substantial computational overhead of FHE makes it impractical for…
Early-exit neural networks have become popular for reducing inference latency by allowing intermediate predictions when sufficient confidence is achieved. However, standard approaches typically rely on single-model confidence thresholds,…
Weight-sharing (WS) has recently emerged as a paradigm to accelerate the automated search for efficient neural architectures, a process dubbed Neural Architecture Search (NAS). Although very appealing, this framework is not without…
Digital mapping of semantic features is essential for achieving interoperability between semantic communication and practical digital infrastructure. However, current research efforts predominantly concentrate on analog semantic…
With the success of self-supervised learning (SSL), it has become a mainstream paradigm to fine-tune from self-supervised pretrained models to boost the performance on downstream tasks. However, we find that current SSL models suffer severe…
Current Serverless abstractions (e.g., FaaS) poorly support non-functional requirements (e.g., QoS and constraints), are provider-dependent, and are incompatible with other cloud abstractions (e.g., databases). As a result, application…
Vision transformers have recently gained great success on various computer vision tasks; nevertheless, their high model complexity makes it challenging to deploy on resource-constrained devices. Quantization is an effective approach to…
Test-time compute scaling has emerged as a new axis along which to improve model accuracy, where additional computation is used at inference time to allow the model to think longer for more challenging problems. One promising approach for…
Vector search and database systems have become a keystone component in many AI applications. While many prior research has investigated how to accelerate the performance of generic vector search, emerging AI applications require running…